Download postprocessing/flashvsr/sparse_sage/__init__.py from 1ripon1/ColabWan: direct link, hf CLI and curl.
- Browser
- Download file 362 Bytes
-
https://huggingface.co/spaces/1ripon1/ColabWan/resolve/main/postprocessing/flashvsr/sparse_sage/__init__.py
- Command line
-
hf download hf://spaces/1ripon1/ColabWan/postprocessing/flashvsr/sparse_sage/__init__.py
-
curl -L -o __init__.py https://huggingface.co/spaces/1ripon1/ColabWan/resolve/main/postprocessing/flashvsr/sparse_sage/__init__.py
362 Bytes
| """ | |
| Sparse SageAttention module for efficient attention computation. | |
| This module provides sparse attention mechanisms with INT8 quantization | |
| and Triton kernel implementations for improved performance. | |
| Copyright (c) 2024 by SageAttention team. | |
| Licensed under the Apache License, Version 2.0 | |
| """ | |
| from .core import sparse_sageattn | |
| __all__ = ['sparse_sageattn'] | |